{"id":"https://openalex.org/W3096723250","doi":"https://doi.org/10.1109/icassp39728.2021.9414880","title":"Emotion Recognition by Fusing Time Synchronous and Time Asynchronous Representations","display_name":"Emotion Recognition by Fusing Time Synchronous and Time Asynchronous Representations","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3096723250","doi":"https://doi.org/10.1109/icassp39728.2021.9414880","mag":"3096723250"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.14102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079268196","display_name":"Wen Wu","orcid":"https://orcid.org/0000-0001-8116-7715"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Wen Wu","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip C. Woodland","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079268196"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":8.3891,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.98065039,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6269","last_page":"6273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7945308685302734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6517694592475891},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6291571259498596},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5998351573944092},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5757333636283875},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5200721621513367},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5093759298324585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4858498275279999},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39811253547668457},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36731860041618347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945308685302734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6517694592475891},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6291571259498596},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5998351573944092},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5757333636283875},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5200721621513367},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5093759298324585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4858498275279999},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39811253547668457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36731860041618347},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.14102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14102","pdf_url":"https://arxiv.org/pdf/2010.14102","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.14102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14102","pdf_url":"https://arxiv.org/pdf/2010.14102","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321848","display_name":"Cambridge Trust","ror":"https://ror.org/05sprqy15"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W99485238","https://openalex.org/W141927798","https://openalex.org/W943204654","https://openalex.org/W1965069145","https://openalex.org/W2009059481","https://openalex.org/W2028975938","https://openalex.org/W2085628288","https://openalex.org/W2146334809","https://openalex.org/W2156146072","https://openalex.org/W2164699598","https://openalex.org/W2250539671","https://openalex.org/W2551548999","https://openalex.org/W2584561145","https://openalex.org/W2597655663","https://openalex.org/W2610961739","https://openalex.org/W2795986449","https://openalex.org/W2797947982","https://openalex.org/W2896457183","https://openalex.org/W2937584914","https://openalex.org/W2962770129","https://openalex.org/W2963104701","https://openalex.org/W2963341956","https://openalex.org/W2963386218","https://openalex.org/W2963466847","https://openalex.org/W2963654251","https://openalex.org/W2963702064","https://openalex.org/W2963962398","https://openalex.org/W2966518489","https://openalex.org/W2973034847","https://openalex.org/W2997258743","https://openalex.org/W3015240477","https://openalex.org/W3015489952","https://openalex.org/W3015707499","https://openalex.org/W3015964358","https://openalex.org/W3148978181","https://openalex.org/W4299280181","https://openalex.org/W6657744143","https://openalex.org/W6735377749","https://openalex.org/W6750449527","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W1998701884","https://openalex.org/W3134175397","https://openalex.org/W2597655663"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,19,25,60,77,169],"novel":[4],"two-branch":[5,107],"neural":[6],"network":[7],"model":[8],"structure":[9,108],"is":[10,134],"proposed":[11],"for":[12,152,171],"multimodal":[13],"emotion":[14,88,174],"recognition,":[15],"which":[16],"consists":[17],"of":[18,79,128],"time":[20,26,57],"synchronous":[21],"branch":[22,28],"(TSB)":[23],"and":[24,36,44,52,94],"asynchronous":[27],"(TAB).":[29],"To":[30],"capture":[31],"correlations":[32],"between":[33],"each":[34,48],"word":[35],"its":[37],"acoustic":[38],"realisation,":[39],"the":[40,92,95,101,106,137,154,157],"TSB":[41,93],"combines":[42],"speech":[43,123],"text":[45,74],"modalities":[46],"at":[47],"input":[49],"window":[50],"frame":[51],"then":[53],"uses":[54,90],"pooling":[55],"across":[56],"to":[58],"form":[59],"single":[61],"embedding":[62,84],"vector.":[63,85],"The":[64,86],"TAB,":[65],"by":[66,71,147],"contrast,":[67],"provides":[68],"cross-utterance":[69,138],"information":[70,139],"integrating":[72],"sentence":[73],"embeddings":[75],"from":[76],"number":[78],"context":[80],"utterances":[81],"into":[82],"another":[83],"final":[87,158],"classification":[89,114,160],"both":[91],"TAB":[96],"embeddings.":[97],"Experimental":[98],"results":[99,111],"on":[100],"IEMOCAP":[102],"dataset":[103],"demonstrate":[104],"that":[105,136],"achieves":[109],"state-of-the-art":[110],"in":[112],"4-way":[113],"with":[115,162],"all":[116,153],"common":[117],"test":[118],"setups.":[119],"When":[120],"using":[121],"automatic":[122],"recognition":[124,175],"(ASR)":[125],"output":[126],"instead":[127],"manually":[129],"transcribed":[130],"reference":[131],"text,":[132],"it":[133],"shown":[135],"considerably":[140],"improves":[141],"robustness":[142],"against":[143],"ASR":[144,163],"errors.":[145],"Furthermore,":[146],"incorporating":[148],"an":[149],"extra":[150],"class":[151],"other":[155],"emotions,":[156],"5-way":[159],"system":[161],"hypotheses":[164],"can":[165],"be":[166],"viewed":[167],"as":[168],"prototype":[170],"more":[172],"realistic":[173],"systems.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}